library(tidyverse) # for data cleaning and plotting
## ── Attaching packages ──────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2 ✓ purrr 0.3.4
## ✓ tibble 3.0.3 ✓ dplyr 1.0.2
## ✓ tidyr 1.1.2 ✓ stringr 1.4.0
## ✓ readr 1.3.1 ✓ forcats 0.5.0
## ── Conflicts ─────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(googlesheets4) # for reading googlesheet data
library(lubridate) # for date manipulation
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
library(openintro) # for the abbr2state() function
## Loading required package: airports
## Loading required package: cherryblossom
## Loading required package: usdata
library(palmerpenguins)# for Palmer penguin data
library(maps) # for map data
##
## Attaching package: 'maps'
## The following object is masked from 'package:purrr':
##
## map
library(ggmap) # for mapping points on maps
## Google's Terms of Service: https://cloud.google.com/maps-platform/terms/.
## Please cite ggmap if you use it! See citation("ggmap") for details.
library(gplots) # for col2hex() function
##
## Attaching package: 'gplots'
## The following object is masked from 'package:stats':
##
## lowess
library(RColorBrewer) # for color palettes
library(sf) # for working with spatial data
## Linking to GEOS 3.8.1, GDAL 3.1.1, PROJ 6.3.1
library(leaflet) # for highly customizable mapping
library(carData) # for Minneapolis police stops data
library(ggthemes) # for more themes (including theme_map())
gs4_deauth() # To not have to authorize each time you knit.
theme_set(theme_minimal())
# Starbucks locations
Starbucks <- read_csv("https://www.macalester.edu/~ajohns24/Data/Starbucks.csv")
## Parsed with column specification:
## cols(
## Brand = col_character(),
## `Store Number` = col_character(),
## `Store Name` = col_character(),
## `Ownership Type` = col_character(),
## `Street Address` = col_character(),
## City = col_character(),
## `State/Province` = col_character(),
## Country = col_character(),
## Postcode = col_character(),
## `Phone Number` = col_character(),
## Timezone = col_character(),
## Longitude = col_double(),
## Latitude = col_double()
## )
starbucks_us_by_state <- Starbucks %>%
filter(Country == "US") %>%
count(`State/Province`) %>%
mutate(state_name = str_to_lower(abbr2state(`State/Province`)))
# Lisa's favorite St. Paul places - example for you to create your own data
favorite_stp_by_lisa <- tibble(
place = c("Home", "Macalester College", "Adams Spanish Immersion",
"Spirit Gymnastics", "Bama & Bapa", "Now Bikes",
"Dance Spectrum", "Pizza Luce", "Brunson's"),
long = c(-93.1405743, -93.1712321, -93.1451796,
-93.1650563, -93.1542883, -93.1696608,
-93.1393172, -93.1524256, -93.0753863),
lat = c(44.950576, 44.9378965, 44.9237914,
44.9654609, 44.9295072, 44.9436813,
44.9399922, 44.9468848, 44.9700727)
)
#COVID-19 data from the New York Times
covid19 <- read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-states.csv")
## Parsed with column specification:
## cols(
## date = col_date(format = ""),
## state = col_character(),
## fips = col_character(),
## cases = col_double(),
## deaths = col_double()
## )
These exercises will reiterate what you learned in the “Mapping data with R” tutorial. If you haven’t gone through the tutorial yet, you should do that first.
ggmap)Starbucks locations to a world map. Add an aesthetic to the world map that sets the color of the points according to the ownership type. What, if anything, can you deduce from this visualization?world <- get_stamenmap(
bbox = c(left = -180, bottom = -57, right = 179, top = 82.1),
maptype = "terrain",
zoom = 2)
## Source : http://tile.stamen.com/terrain/2/0/0.png
## Source : http://tile.stamen.com/terrain/2/1/0.png
## Source : http://tile.stamen.com/terrain/2/2/0.png
## Source : http://tile.stamen.com/terrain/2/3/0.png
## Source : http://tile.stamen.com/terrain/2/0/1.png
## Source : http://tile.stamen.com/terrain/2/1/1.png
## Source : http://tile.stamen.com/terrain/2/2/1.png
## Source : http://tile.stamen.com/terrain/2/3/1.png
## Source : http://tile.stamen.com/terrain/2/0/2.png
## Source : http://tile.stamen.com/terrain/2/1/2.png
## Source : http://tile.stamen.com/terrain/2/2/2.png
## Source : http://tile.stamen.com/terrain/2/3/2.png
ggmap(world) +
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude, color = `Ownership Type`),
alpha = .3,
size = .1) +
theme_map() +
theme(legend.background = element_blank())
## Warning: Removed 1 rows containing missing values (geom_point).
Twin_Cities <- get_stamenmap(
bbox = c(left = -93.67, bottom = 44.75, right = -92.59, top = 45.18),
maptype = "terrain",
zoom = 11)
## Source : http://tile.stamen.com/terrain/11/491/735.png
## Source : http://tile.stamen.com/terrain/11/492/735.png
## Source : http://tile.stamen.com/terrain/11/493/735.png
## Source : http://tile.stamen.com/terrain/11/494/735.png
## Source : http://tile.stamen.com/terrain/11/495/735.png
## Source : http://tile.stamen.com/terrain/11/496/735.png
## Source : http://tile.stamen.com/terrain/11/497/735.png
## Source : http://tile.stamen.com/terrain/11/491/736.png
## Source : http://tile.stamen.com/terrain/11/492/736.png
## Source : http://tile.stamen.com/terrain/11/493/736.png
## Source : http://tile.stamen.com/terrain/11/494/736.png
## Source : http://tile.stamen.com/terrain/11/495/736.png
## Source : http://tile.stamen.com/terrain/11/496/736.png
## Source : http://tile.stamen.com/terrain/11/497/736.png
## Source : http://tile.stamen.com/terrain/11/491/737.png
## Source : http://tile.stamen.com/terrain/11/492/737.png
## Source : http://tile.stamen.com/terrain/11/493/737.png
## Source : http://tile.stamen.com/terrain/11/494/737.png
## Source : http://tile.stamen.com/terrain/11/495/737.png
## Source : http://tile.stamen.com/terrain/11/496/737.png
## Source : http://tile.stamen.com/terrain/11/497/737.png
## Source : http://tile.stamen.com/terrain/11/491/738.png
## Source : http://tile.stamen.com/terrain/11/492/738.png
## Source : http://tile.stamen.com/terrain/11/493/738.png
## Source : http://tile.stamen.com/terrain/11/494/738.png
## Source : http://tile.stamen.com/terrain/11/495/738.png
## Source : http://tile.stamen.com/terrain/11/496/738.png
## Source : http://tile.stamen.com/terrain/11/497/738.png
ggmap(Twin_Cities) +
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude, color = `Ownership Type`),
size = 3) +
theme_map() +
theme(legend.background = element_blank())
## Warning: Removed 25469 rows containing missing values (geom_point).
The zoom number allows us to include more or less details in the plot. If the zoom number is small then it shows less detail, if the zoom number is large then it shows more detail.
get_stamenmap() in help and look at maptype). Include a map with one of the other map types.Different maptypes available with get_stamenmap: “terrain”, “terrain-background”, “terrain-labels”, “terrain-lines”, “toner”, “toner-2010”, “toner-2011”, “toner-background”, “toner-hybrid”, “toner-labels”, “toner-lines”, “toner-lite”, “watercolor”
Twin_Cities <- get_stamenmap(
bbox = c(left = -93.67, bottom = 44.75, right = -92.59, top = 45.18),
maptype = "toner-2011",
zoom = 11)
## Source : http://tile.stamen.com/toner-2011/11/491/735.png
## Source : http://tile.stamen.com/toner-2011/11/492/735.png
## Source : http://tile.stamen.com/toner-2011/11/493/735.png
## Source : http://tile.stamen.com/toner-2011/11/494/735.png
## Source : http://tile.stamen.com/toner-2011/11/495/735.png
## Source : http://tile.stamen.com/toner-2011/11/496/735.png
## Source : http://tile.stamen.com/toner-2011/11/497/735.png
## Source : http://tile.stamen.com/toner-2011/11/491/736.png
## Source : http://tile.stamen.com/toner-2011/11/492/736.png
## Source : http://tile.stamen.com/toner-2011/11/493/736.png
## Source : http://tile.stamen.com/toner-2011/11/494/736.png
## Source : http://tile.stamen.com/toner-2011/11/495/736.png
## Source : http://tile.stamen.com/toner-2011/11/496/736.png
## Source : http://tile.stamen.com/toner-2011/11/497/736.png
## Source : http://tile.stamen.com/toner-2011/11/491/737.png
## Source : http://tile.stamen.com/toner-2011/11/492/737.png
## Source : http://tile.stamen.com/toner-2011/11/493/737.png
## Source : http://tile.stamen.com/toner-2011/11/494/737.png
## Source : http://tile.stamen.com/toner-2011/11/495/737.png
## Source : http://tile.stamen.com/toner-2011/11/496/737.png
## Source : http://tile.stamen.com/toner-2011/11/497/737.png
## Source : http://tile.stamen.com/toner-2011/11/491/738.png
## Source : http://tile.stamen.com/toner-2011/11/492/738.png
## Source : http://tile.stamen.com/toner-2011/11/493/738.png
## Source : http://tile.stamen.com/toner-2011/11/494/738.png
## Source : http://tile.stamen.com/toner-2011/11/495/738.png
## Source : http://tile.stamen.com/toner-2011/11/496/738.png
## Source : http://tile.stamen.com/toner-2011/11/497/738.png
ggmap(Twin_Cities) +
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude, color = `Ownership Type`),
size = 3) +
theme_map() +
theme(legend.background = element_blank())
## Warning: Removed 25469 rows containing missing values (geom_point).
annotate() function (see ggplot2 cheatsheet).Twin_Cities <- get_stamenmap(
bbox = c(left = -93.67, bottom = 44.75, right = -92.59, top = 45.18),
maptype = "toner-2011",
zoom = 11)
ggmap(Twin_Cities) +
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude, color = `Ownership Type`),
size = 3) +
theme_map() +
theme(legend.background = element_blank()) +
annotate(geom = "text", x = -93.1712321, y = 44.9308890, label = "Macalester College") +
annotate(geom = "point", x = -93.1712321, y = 44.9378965, color = "Dark Blue", size = 3)
## Warning: Removed 25469 rows containing missing values (geom_point).
geom_map())The example I showed in the tutorial did not account for population of each state in the map. In the code below, a new variable is created, starbucks_per_10000, that gives the number of Starbucks per 10,000 people. It is in the starbucks_with_2018_pop_est dataset.
census_pop_est_2018 <- read_csv("https://www.dropbox.com/s/6txwv3b4ng7pepe/us_census_2018_state_pop_est.csv?dl=1") %>%
separate(state, into = c("dot","state"), extra = "merge") %>%
select(-dot) %>%
mutate(state = str_to_lower(state))
## Parsed with column specification:
## cols(
## state = col_character(),
## est_pop_2018 = col_double()
## )
starbucks_with_2018_pop_est <-
starbucks_us_by_state %>%
left_join(census_pop_est_2018,
by = c("state_name" = "state")) %>%
mutate(starbucks_per_10000 = (n/est_pop_2018)*10000)
dplyr review: Look through the code above and describe what each line of code does.Line : Reads in the US Census 2018 Estimated State Population Number line : Separates the dot and the state from each other, then merges the state name. Due to the separation, the default would otherwise leave out the second word of a state with two words in its name, such as New Mexico and New Jersey line : Deletes the dot as a column line : Mutates all state names to lower cases line : This line of code saves starbucks_us_by_state to starbucks_with_2018_pop_est line : Left join of the Census Population Estimate 2018 data set by state name line : We create a new variable called starbucks_per_1000 which first divides the total number of Starbucks in a state by the estimated population number in 2018, and then multiplies that number by 10,000.
states_map <- map_data("state")
starbucks_with_2018_pop_est %>%
ggplot() +
geom_map(map = states_map,
aes(map_id = state_name,
fill = starbucks_per_10000)) +
geom_point(data = Starbucks %>% filter(!`State/Province` %in% c("HI", "AK"), `Country` == "US"),
aes(x = Longitude, y = Latitude),
size = .05,
alpha = .2,
color = "goldenrod") +
expand_limits(x = states_map$long, y = states_map$lat) +
labs(title = "Starbucks in the United States",
caption = "Created by Floyd Krom") +
theme(legend.background = element_blank()) +
theme_map() +
scale_fill_viridis_c()
leaflet)tibble() function that has 10-15 rows of your favorite places. The columns will be the name of the location, the latitude, the longitude, and a column that indicates if it is in your top 3 favorite locations or not. For an example of how to use tibble(), look at the favorite_stp_by_lisa I created in the data R code chunk at the beginning.favorite_step_by_floyd <- tibble(
place = c("Neighborhood Development Center", "Los Ocampo", "Allianz Field", "Home", "Stone Arch Bridge", "Trader Joe's", "Midtown Global Market", "Wakame Sushi & Asian Bistro", "Macalester College", "Starks Clips"),
long = c(-93.128475, -93.125621, -93.165083, -93.246913, -93.253369, -93.258221, -93.260421, -93.321944, -93.1712321, -93.164284),
lat = c(44.956134, 44.956154, 44.953209, 44.981674, 44.980943, 44.976722, 44.948709, 44.947059, 44.9378965, 44.940497),
favorite_place = c("No", "No", "No", "No", "Yes", "No", "Yes", "No", "No", "Yes")
)
leaflet map that uses circles to indicate your favorite places. Label them with the name of the place. Choose the base map you like best. Color your 3 favorite places differently than the ones that are not in your top 3 (HINT: colorFactor()). Add a legend that explains what the colors mean. pal <- colorFactor(
palette = c("#111D4A", "#5998C5"),
domain = favorite_step_by_floyd$favorite_place)
leaflet(data = favorite_step_by_floyd) %>%
addProviderTiles(providers$CartoDB.DarkMatter) %>%
addCircles(lng = ~long,
lat = ~lat,
label = ~place,
weight = 10,
opacity = 1,
color = ~pal(favorite_place)) %>%
addLegend(pal = pal,
values = ~favorite_place,
opacity = 1,
title = "Favorite Place",
position = "bottomright") %>%
addPolylines(lng = ~long,
lat = ~lat,
color = c("#829399"))
This section will revisit some datasets we have used previously and bring in a mapping component.
The data come from Washington, DC and cover the last quarter of 2014.
Two data tables are available:
Trips contains records of individual rentalsStations gives the locations of the bike rental stationsHere is the code to read in the data. We do this a little differently than usualy, which is why it is included here rather than at the top of this file. To avoid repeatedly re-reading the files, start the data import chunk with {r cache = TRUE} rather than the usual {r}. This code reads in the large dataset right away.
data_site <-
"https://www.macalester.edu/~dshuman1/data/112/2014-Q4-Trips-History-Data.rds"
Trips <- readRDS(gzcon(url(data_site)))
Stations<-read_csv("http://www.macalester.edu/~dshuman1/data/112/DC-Stations.csv")
## Parsed with column specification:
## cols(
## name = col_character(),
## lat = col_double(),
## long = col_double(),
## nbBikes = col_double(),
## nbEmptyDocks = col_double()
## )
Stations to make a visualization of the total number of departures from each station in the Trips data. Use either color or size to show the variation in number of departures. This time, plot the points on top of a map. Use any of the mapping tools you’d like.Stations2 <- Stations %>%
left_join(Trips,
by = c("name" = "sstation")) %>%
group_by(long, lat) %>%
summarize(total_departures = n())
## `summarise()` regrouping output by 'long' (override with `.groups` argument)
Washington_DC <- get_stamenmap(
bbox = c(left = -77.1732, bottom = 38.8159, right = -76.7990, top = 39.0058),
maptype = "toner-2011",
zoom = 11)
## Source : http://tile.stamen.com/toner-2011/11/584/782.png
## Source : http://tile.stamen.com/toner-2011/11/585/782.png
## Source : http://tile.stamen.com/toner-2011/11/586/782.png
## Source : http://tile.stamen.com/toner-2011/11/587/782.png
## Source : http://tile.stamen.com/toner-2011/11/584/783.png
## Source : http://tile.stamen.com/toner-2011/11/585/783.png
## Source : http://tile.stamen.com/toner-2011/11/586/783.png
## Source : http://tile.stamen.com/toner-2011/11/587/783.png
## Source : http://tile.stamen.com/toner-2011/11/584/784.png
## Source : http://tile.stamen.com/toner-2011/11/585/784.png
## Source : http://tile.stamen.com/toner-2011/11/586/784.png
## Source : http://tile.stamen.com/toner-2011/11/587/784.png
ggmap(Washington_DC) +
geom_point(data = Stations2,
aes(x = long, y = lat, color = total_departures),
size = 3) +
theme_map() +
theme(legend.background = element_blank())
## Warning: Removed 32 rows containing missing values (geom_point).
scale_color_viridis_c()
## <ScaleContinuous>
## Range:
## Limits: 0 -- 1
Stations2 <- Stations %>%
left_join(Trips,
by = c("name" = "sstation")) %>%
group_by(long, lat) %>%
summarize(percent_casual= mean(client == "Casual"))
## `summarise()` regrouping output by 'long' (override with `.groups` argument)
Washington_DC <- get_stamenmap(
bbox = c(left = -77.1732, bottom = 38.8159, right = -76.7990, top = 39.0058),
maptype = "toner-2011",
zoom = 11)
ggmap(Washington_DC) +
geom_point(data = Stations2,
aes(x = long, y = lat, color = percent_casual),
size = 3) +
theme_map() +
scale_color_viridis_c()
## Warning: Removed 32 rows containing missing values (geom_point).
As I guessed in problem set 3, there is a high percentage of casual riders that rent out their bikes from stations in the downtown area, especially along the river. It is very common for tourists exploring the city, which can be identified as casual riders, to take a bike ride along a scenic river route. This therefore explains the high percentage of casual riders at these stations in the downtown area and along the river side of the downtown area.
The following exercises will use the COVID-19 data from the NYT.
states_map <- map_data("state")
covid19 %>%
group_by(state) %>%
summarize(cumulative_cases = max(cases)) %>%
mutate(state = str_to_lower(state)) %>%
ggplot(aes(fill = cumulative_cases)) +
geom_map(map = states_map,
aes(map_id = state)) +
expand_limits(x = states_map$long, y = states_map$lat) +
labs(title = "Cumulative COVID-19 cases in the United States") +
theme(legend.background = element_blank()) +
theme_map() +
scale_fill_viridis_c()
## `summarise()` ungrouping output (override with `.groups` argument)
In this visualization, the number of COVID-19 cases are not proportional to the population number in each state, therefore this visualization is not necessarily a fair way to compare states.
covid19_population <-
covid19 %>%
mutate(state = str_to_lower(state)) %>%
left_join(census_pop_est_2018,
by = "state") %>%
group_by(state, est_pop_2018) %>%
summarize(cumulative_cases = max(cases)) %>%
mutate(cases_per_10000 = (cumulative_cases/est_pop_2018)*10000)
## `summarise()` regrouping output by 'state' (override with `.groups` argument)
states_map <- map_data("state")
covid19_population %>%
mutate(state = str_to_lower(state)) %>%
ggplot() +
geom_map(map = states_map,
aes(map_id = state, fill = cases_per_10000)) +
expand_limits(x = states_map$long, y = states_map$lat) +
labs(title = "Cumulative COVID-19 cases per 10,000 people in the United States") +
theme(legend.background = element_blank()) +
theme_map() +
scale_fill_viridis_c()
covid19_date <-
covid19 %>%
filter(date %in% ymd(c("2020-04-04", "2020-06-14", "2020-07-17", "2020-09-25"))) %>%
mutate(state = str_to_lower(state)) %>%
left_join(census_pop_est_2018,
by = "state") %>%
mutate(cases_per_10000 = (cases/est_pop_2018)*10000)
covid19_date %>%
mutate(state = str_to_lower(state)) %>%
ggplot() +
geom_map(map = states_map,
aes(map_id = state, fill = cases_per_10000)) +
expand_limits(x = states_map$long, y = states_map$lat) +
facet_wrap(~date) +
labs(title = "Cumulative COVID-19 cases per 10,000 people in the United States") +
theme_map() +
theme(legend.background = element_blank()) +
scale_fill_viridis_c()
This exercise uses the datasets MplsStops and MplsDemo from the carData library. Search for them in Help to find out more information.
MplsStops dataset to find out how many stops there were for each neighborhood and the proportion of stops that were for a suspicious vehicle or person. Sort the results from most to least number of stops. Save this as a dataset called mpls_suspicious and display the table.mpls_suspicious <- MplsStops %>%
group_by(neighborhood) %>%
count(problem) %>%
mutate(proportion_suspicious = n/sum(n)) %>%
filter(problem == "suspicious")
mpls_suspicious %>%
arrange(desc(n))
leaflet map and the MplsStops dataset to display each of the stops on a map as a small point. Color the points differently depending on whether they were for suspicious vehicle/person or a traffic stop (the problem variable). HINTS: use addCircleMarkers, set stroke = FAlSE, use colorFactor() to create a palette. pal <- colorFactor(
palette = "viridis",
domain = MplsStops$problem)
leaflet(data = MplsStops,
options = leafletOptions(preferCanvas = TRUE)) %>%
addProviderTiles(providers$Stamen.TonerHybrid,
options = providerTileOptions(updateWhenZooming = FALSE,updateWhenIdle = TRUE)) %>%
addCircles(lng = ~long,
lat = ~lat,
label = ~problem,
weight = 10,
stroke = FALSE,
opacity = 1,
color = ~pal(problem)) %>%
addLegend(pal = pal,
values = ~problem,
opacity = 1,
title = "Problem",
position = "bottomright")
eval=FALSE. Although it looks like it only links to the .sph file, you need the entire folder of files to create the mpls_nbhd data set. These data contain information about the geometries of the Minneapolis neighborhoods. Using the mpls_nbhd dataset as the base file, join the mpls_suspicious and MplsDemo datasets to it by neighborhood (careful, they are named different things in the different files). Call this new dataset mpls_all.mpls_nbhd <- st_read("Minneapolis_Neighborhoods/Minneapolis_Neighborhoods.shp", quiet = TRUE)
mpls_all<-
mpls_nbhd %>%
st_as_sf(coords = c("long", "lat"), crs = "NAD27") %>%
group_by(BDNAME) %>%
summarise(geometry = st_combine(geometry)) %>%
st_cast("POLYGON") %>%
left_join(mpls_suspicious,
by = c("BDNAME" = "neighborhood")) %>%
left_join(MplsDemo,
by = c("BDNAME" = "neighborhood"))
## `summarise()` ungrouping output (override with `.groups` argument)
## Warning in st_cast.sf(., "POLYGON"): repeating attributes for all sub-geometries
## for which they may not be constant
leaflet to create a map from the mpls_all data that colors the neighborhoods by prop_suspicious. Display the neighborhood name as you scroll over it. Describe what you observe in the map.palette_mpls_all <- colorNumeric("Blues", domain = mpls_all$proportion_suspicious)
leaflet(data = mpls_all) %>%
addProviderTiles(providers$Esri.WorldStreetMap) %>%
addPolygons(label = ~BDNAME,
fillColor = ~palette_mpls_all(proportion_suspicious),
stroke = FALSE,
fillOpacity = .8,
highlight = highlightOptions(color = "block",
fillOpacity = .9,
bringToFront = FALSE)) %>%
addLegend(pal = palette_mpls_all,
values = ~proportion_suspicious,
opacity = 0.5,
title = NULL,
position = "bottomright")
leaflet to create a map of your own choosing. Come up with a question you want to try to answer and use the map to help answer that question. Describe what your map shows.DID YOU REMEMBER TO UNCOMMENT THE OPTIONS AT THE TOP?